The invention discloses a method for correcting one or more error characters in results of speech recognition, the method comprising the steps of: marking the one or more error characters in the speech recognition results; inputting one or more correct characters corresponding to the one or more marked error characters by input based on character-shape; recognizing the input based on character-shape; displaying one or more candidate characters; selecting one or more desired characters from the one or more candidate characters in accordance with the user; and replacing the one or more error characters with the one or more selected characters; the method characterized by further comprising the step of filtering the one or more candidate characters in accordance with acoustic information associated with the one or more error characters.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method for correcting one or more error characters in results of speech recognition, the method comprising the steps of: marking the one or more error characters in the speech recognition results; inputting one or more correct characters corresponding to the one or more marked error characters by input based on character-shape; recognizing the input based on character-shape; displaying one or more candidate characters; selecting one or more desired characters from the one or more candidate characters in accordance with the user; and replacing the one or more error characters with the one or more selected characters; the method characterized by further comprising the step of filtering the one or more candidate characters in accordance with acoustic information associated with the one or more error characters.
2. The method of claim 1 , wherein the speech recognition is Chinese speech recognition, and the characters are Chinese characters, Chinese words or the combination thereof.
3. The method of claim 1 , wherein the acoustic information associated with the one or more error characters is obtained from the user's dictation of a speech recognition phase.
4. The method of claim 1 , wherein the acoustic information of the one or more error characters is obtained from the user's dictation of an error correction phase.
5. The method of claim 1 , wherein the acoustic information is an acoustic model from a confusion matrix.
6. The method of claim 5 , wherein the acoustic model cooperates with a language model of a character or a word level to filter the one or more candidate characters.
7. The method of claim 1 , wherein the one or more candidate characters are organized as a tree, and the tree is pruned by the acoustic information.
8. The method of claim 7 , wherein the acoustic information is an acoustic model from a confusion matrix.
9. The method of claim 8 , wherein the acoustic model cooperates with a language model of a character or a word level to prune the tree.
10. The method of claim 1 , wherein the one or more candidate characters are integrated with a virtual stroke keyboard on a display screen.
11. A speech recognition system capable of correcting one or more error characters in results of speech recognition, the system comprising: voice detection means for collecting a speech sample of a user; pronunciation probability calculation means, which, for each pronunciation in an acoustic model, gives a probability estimation value of whether the pronunciation is the same as the speech sample; word probability calculation means, which, according to a language model, gives a probability estimation value of a word occurring in a current context; word matching means for calculating a joint probability through combining a probability value calculated by the pronunciation probability calculation means with a probability value calculated by the word probability calculation means and taking the word with the greatest joint probability value as the result of the speech recognition; context generating means for modifying the current context by using the speech recognition result; and, word output means; the speech recognition system characterized by further comprising error correction means, user marking the one or more error characters in the results of the speech recognition via the error correction means, inputting one or more correct characters corresponding to the one or more error characters by input based on characters-shape, and the error correction means recognizing the input, generating one or more candidate characters and filtering the one or more candidate characters via acoustic information associated with the one or more error characters.
12. The system of claim 11 , wherein the speech recognition is Chinese speech recognition, and the characters are Chinese characters, Chinese words or the combination thereof.
13. The system of claim 11 , wherein the acoustic information associated with the one or more error characters is obtained from the user's dictation of a speech recognition phase.
14. The system of claim 11 , wherein the acoustic information associated with the one or more error characters is obtained from the user's dictation of an error correction phase.
15. The system of claim 11 , wherein the acoustic information is an acoustic model from a confusion matrix.
16. The system of claim 15 , wherein the acoustic model cooperates with a language model of a character or a word level to filter the one or more candidate characters.
17. The system of claim 11 , wherein the one or more candidate characters are organized as a tree, and the tree is pruned by the acoustic information.
18. The system of claim 17 , wherein the acoustic information is an acoustic model from a confusion matrix.
19. The system of claim 18 , wherein the acoustic model cooperates with a language model of a character or a word level to pruned the tree.
20. The system of claim 11 , wherein the one or more candidate characters are integrated with a virtual stroke keyboard on a display screen.
21. Apparatus for correcting one or more error characters in results of speech recognition, the apparatus comprising: at least one processor operative to: (i) mark the one or more error characters in the speech recognition results; (ii) input one or more correct characters corresponding to the one or more marked error characters by input based on character-shape; (iii) recognize the input based on character-shape; (iv) display one or more candidate characters; (v) select one or more desired characters from the one or more candidate characters in accordance with the user; and (vi) replace the one or more error characters with the one or more selected characters; (vii) the apparatus characterized by the at least one processor being further operative to filter the one or more candidate characters in accordance with acoustic information associated with the one or more error characters.
22. An article of manufacture for correcting one or more error characters in results of speech recognition, comprising a machine readable medium containing one or more programs which when executed implement the steps of: marking the one or more error characters in the speech recognition results; inputting one or more correct characters corresponding to the one or more marked error characters by input based on character-shape; recognizing the input based on character-shape; displaying one or more candidate characters; selecting one or more desired characters from the one or more candidate characters in accordance with the user; and replacing the one or more error characters with the one or more selected characters; the article of manufacture characterized by further comprising the step of filtering the one or more candidate characters in accordance with acoustic information associated with the one or more error characters.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 25, 2000
January 28, 2003
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.